Road Topology Refinement via a Multi-Conditional Generative Adversarial Network
With the rapid development of intelligent transportation, there comes huge demands for high-precision road network maps. However, due to the complex road spectral performance, it is very challenging to extract road networks with complete topologies. Based on the topological networks produced by prev...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/19/5/1162 |
| _version_ | 1798043641558597632 |
|---|---|
| author | Yang Zhang Xiang Li Qianyu Zhang |
| author_facet | Yang Zhang Xiang Li Qianyu Zhang |
| author_sort | Yang Zhang |
| collection | DOAJ |
| description | With the rapid development of intelligent transportation, there comes huge demands for high-precision road network maps. However, due to the complex road spectral performance, it is very challenging to extract road networks with complete topologies. Based on the topological networks produced by previous road extraction methods, in this paper, we propose a Multi-conditional Generative Adversarial Network (McGAN) to obtain complete road networks by refining the imperfect road topology. The proposed McGAN, which is composed of two discriminators and a generator, takes both original remote sensing image and the initial road network produced by existing road extraction methods as input. The first discriminator employs the original spectral information to instruct the reconstruction, and the other discriminator aims to refine the road network topology. Such a structure makes the generator capable of receiving both spectral and topological information of the road region, thus producing more complete road networks compared with the initial road network. Three different datasets were used to compare McGan with several recent approaches, which showed that the proposed method significantly improved the precision and recall of the road networks, and also worked well for those road regions where previous methods could hardly obtain complete structures. |
| first_indexed | 2024-04-11T22:51:54Z |
| format | Article |
| id | doaj.art-89b147cf68ce46d88da2a956fb645869 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T22:51:54Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-89b147cf68ce46d88da2a956fb6458692022-12-22T03:58:34ZengMDPI AGSensors1424-82202019-03-01195116210.3390/s19051162s19051162Road Topology Refinement via a Multi-Conditional Generative Adversarial NetworkYang Zhang0Xiang Li1Qianyu Zhang2School of Electronic Science, National University of Defense Technology (NUDT), Changsha 410073, ChinaSchool of Electronic Science, National University of Defense Technology (NUDT), Changsha 410073, ChinaSchool of Business, University of Leeds, Leeds LS2 9JT, UKWith the rapid development of intelligent transportation, there comes huge demands for high-precision road network maps. However, due to the complex road spectral performance, it is very challenging to extract road networks with complete topologies. Based on the topological networks produced by previous road extraction methods, in this paper, we propose a Multi-conditional Generative Adversarial Network (McGAN) to obtain complete road networks by refining the imperfect road topology. The proposed McGAN, which is composed of two discriminators and a generator, takes both original remote sensing image and the initial road network produced by existing road extraction methods as input. The first discriminator employs the original spectral information to instruct the reconstruction, and the other discriminator aims to refine the road network topology. Such a structure makes the generator capable of receiving both spectral and topological information of the road region, thus producing more complete road networks compared with the initial road network. Three different datasets were used to compare McGan with several recent approaches, which showed that the proposed method significantly improved the precision and recall of the road networks, and also worked well for those road regions where previous methods could hardly obtain complete structures.http://www.mdpi.com/1424-8220/19/5/1162multi-conditional generative adversarial networkroad topology refinementroad network extraction |
| spellingShingle | Yang Zhang Xiang Li Qianyu Zhang Road Topology Refinement via a Multi-Conditional Generative Adversarial Network Sensors multi-conditional generative adversarial network road topology refinement road network extraction |
| title | Road Topology Refinement via a Multi-Conditional Generative Adversarial Network |
| title_full | Road Topology Refinement via a Multi-Conditional Generative Adversarial Network |
| title_fullStr | Road Topology Refinement via a Multi-Conditional Generative Adversarial Network |
| title_full_unstemmed | Road Topology Refinement via a Multi-Conditional Generative Adversarial Network |
| title_short | Road Topology Refinement via a Multi-Conditional Generative Adversarial Network |
| title_sort | road topology refinement via a multi conditional generative adversarial network |
| topic | multi-conditional generative adversarial network road topology refinement road network extraction |
| url | http://www.mdpi.com/1424-8220/19/5/1162 |
| work_keys_str_mv | AT yangzhang roadtopologyrefinementviaamulticonditionalgenerativeadversarialnetwork AT xiangli roadtopologyrefinementviaamulticonditionalgenerativeadversarialnetwork AT qianyuzhang roadtopologyrefinementviaamulticonditionalgenerativeadversarialnetwork |